SpaceXAI: Grok 4.20 Multi-Agent
- by x-ai
- x-ai/grok-4.20-multi-agent
Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...
What the numbers mean
- Context window2,000,000 tokens
- How much the model can read in one request, counting your prompt, any files and the conversation so far. That is about 1,500,000 words, or 3,000 pages.
- Max output1,800,000 tokens
- The longest single reply it can write: about 1,400,000 words.
- Input price$1.25 per million tokens
- What you pay for everything the model reads. A 1,000-word prompt costs less than a cent.
- Output price$2.5 per million tokens
- What you pay for everything the model writes. Output usually costs more than input. A 500-word answer costs less than a cent.
- Modalitiestext, image, file in, text out
- The kinds of content it accepts and the kinds it produces. A model that takes images in can read a screenshot; one that only puts text out cannot draw.
- Knowledge cutoff2025-09-01
- The last date its training data covers. It does not know about anything after that unless you put it in the prompt.
Supported parameters
The settings you can pass with a request. A model that lists tools can call functions; one that lists structured_outputs can be held to a JSON schema.
include_reasoninglogprobsmax_tokensreasoning